Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ce3faec7f7e1a79f00b8dfdced98692bf54047a0ff9fd3ad96c9f8d366eb0e
+oid sha256:072b73b99a99f3e101d5dc0fc19c7b8547b7a659a4d21f6143955b26fb805872
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05438ad0df3fd35feb336af17b2727b5cc735968a239d3fca95b35ba3f8d2de
+oid sha256:54f56addf716dfe5e93a02bbfc8cf9be174baa03ce3bc9caefe11cc1c95898ff
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28934f12b9c2a11845de68b32f74934b975c4c0d6f33f18c99b741ee821528e0
+oid sha256:874cf9f5f3784b600e8a85ba2cac2f2587976308c3e923c97d10b05fa66cc825
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.929431438446045,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.7045454545454546,
+  "best_metric": 1.9179173707962036,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.8465909090909092,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 27.747,
       "eval_steps_per_second": 3.478,
       "step": 1200
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0002,
+      "loss": 2.0524,
+      "step": 1300
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 1.9179173707962036,
+      "eval_runtime": 53.6365,
+      "eval_samples_per_second": 27.817,
+      "eval_steps_per_second": 3.486,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.634363552684032e+16,
+  "total_flos": 3.937833595680768e+16,
   "trial_name": null,
   "trial_params": null
 }